Search AMIA.org

To assess the reliability and confidence calibration of Large Language Models (LLMs) when communicating multi-cancer early detection (MCED) test characteristics in an expert-informed clinical evaluation.

Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, but their clinical benefit is limited by the onset of immune-related adverse events (irAEs). Real-world pharmacovigilance data, such as the FDA's Adverse Event Reporting System (FAERS) database, offer the scale needed to better characterize and understand these toxicities. However, extracting cohorts and normalizing complex fields requires expertise in data preprocessing, technical terminology harmonization, and programming.

This study assessed over 2000 patient perspectives on the use of ambient AI scribes in outpatient visits.

To develop a cohort identification algorithm that captures pregnancy episodes in electronic health record data and characterize demographic and clinical data for eligible patients.

Speech-language delay (SLD) is a developmental condition often identified by pediatricians. While early intervention is recommended, it is common for pediatricians to take a "watch and wait" approach. We sought to assess whether there is discordance between documented concerns and diagnostic coding of SLD and whether discordances differ based on sociodemographic, clinical, and service utilization characteristics.

Virtual hospitals differ from brick-and-mortar hospitals across many elements of the socio-technical work system, particularly their complete reliance on digital tools for communication and care coordination. It is currently unclear whether existing initiatives to improve clinical documentation in brick-and-mortar hospitals are fit for purpose in virtual hospital settings. This study aimed to examine the documentation experiences of clinicians when using technologies to support care delivery in a virtual hospital and [...]

To evaluate whether an electronic health record (EHR) cohort has sufficient data quality to support target trial emulation design elements, using Medicare claims as a reference for billing-derived domains and linked EHR-claims data to illustrate the incremental value of linkage.

Early recognition of unplanned ICU transfer is critical for improving outcomes, yet existing pediatric warning systems lack accuracy and timeliness. We developed machine learning models predicting unplanned ICU transfer up to 24 hours in advance.

High-quality routine health information systems (RHIS) are critical for improving maternal, newborn, and child health (MNCH), to facilitate clinical decision-making and track service delivery. Despite widespread use of health facility data forms for capturing indicators, there are no evidence-based standardized formats or content guidelines for MNCH. The aim of this scoping review was to identify, synthesize, and explore literature related to health facility data forms regarding data-element content, design, and [...]

Machine learning (ML)-based cluster analysis is a common method for subtyping medical conditions and presentations of disease states. Recent advancements in algorithms and increasing access to vast healthcare data have further increased the use of such ML models. However, practical implementation is lacking, largely due to methodological limitations and insufficient reporting and clinical contextualization in the extant literature, with no existing guidelines for this purpose.